© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1563
    Prev
    Next
    INDEX
    Explanations

    uff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quin
    -0.46
     μέ
    -0.45
     pengh
    -0.45
     ké
    -0.44
     manhã
    -0.44
     umum
    -0.43
     administrativos
    -0.43
    manni
    -0.43
    vang
    -0.42
    charAt
    -0.42
    POSITIVE LOGITS
     Efq
    1.30
     myſelf
    1.17
     Monfieur
    1.16
     Majefty
    1.13
     itſelf
    1.11
     Houſe
    1.09
     raiſ
    1.06
     Anſ
    1.06
    ſelf
    1.04
     purpoſe
    1.04
    Activations Density 0.076%

    No Known Activations